3 papers
cs.CV2026
Self-Supervised Learning for Knee Osteoarthritis: Diagnostic Limitations and Prognostic Value of Hospital Data
Haresh Rengaraj Rajamohan, Yuxuan Chen, Kyunghyun Cho +1
This study assesses whether self-supervised learning (SSL) improves knee osteoarthritis (OA) modeling for diagnosis and prognosis relative to ImageNet-pretrained initialization. We…
cs.LG2025
Foundation Models for Clinical Records at Health System Scale
Haresh Rengaraj Rajamohan, Xiang Gao, Weicheng Zhu +5
Large-scale pretraining has transformed modeling of language and other data types, but its potential remains underexplored in healthcare with structured electronic health records (…
eess.IV2025
A Progressive Risk Formulation for Enhanced Deep Learning based Total Knee Replacement Prediction in Knee Osteoarthritis
Haresh Rengaraj Rajamohan, Richard Kijowski, Kyunghyun Cho +1
We developed deep learning models for predicting Total Knee Replacement (TKR) need within various time horizons in knee osteoarthritis patients, with a novel capability: the models…